dead simple document index and search, nothing fancy
-
Updated
Mar 28, 2024 - Python
8000
dead simple document index and search, nothing fancy
Developed an AI-powered document intelligence platform for educators with Google Drive integration, enabling seamless processing of diverse document formats. Leveraged Qdrant vectorization and AzureOpenAI gpt-4o-mini to create a robust question answering system with optimized search capabilities, transparent citations, and direct source navigation.
Programa que simula um algoritmo de indexação de documentos similar ao do Google. Ele é capaz de identificar ocorrências de termos em arquivos TXT.
The purpose of this project is also to compare the efficiency and performance of two different methods for handling search operations: the inverted index and the term-document matrix
It is a search engine that uses json files as corpus of data.
Add a description, image, and links to the document-indexing topic page so that developers can more easily learn about it.
To associate your repository with the document-indexing topic, visit your repo's landing page and select "manage topics."